Demographic classification using image components

Abstract

The present invention includes a system and method for automatically extracting the demographic information from images. The system detects the face in an image, locates different components, extracts component features, and then classifies the components to identify the age, gender, or ethnicity of the person(s) in the image. Using components for demographic classification gives better results as compared to currently known techniques. Moreover, the described system and technique can be used to extract demographic information in more robust manner than currently known methods, in environments where high degree of variability in size, shape, color, texture, pose, and occlusion exists. This invention also performs classifier fusion using Data Level fusion and Multi-level classification for fusing results of various component demographic classifiers. Besides use as an automated data collection system wherein given the necessary facial information as the data, the demographic category of the person is determined automatically, the system could also be used for targeting of the advertisements, surveillance, human computer interaction, security enhancements, immersive computer games and improving user interfaces based on demographic information.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS[0001]This application is entitled to the benefit of Provisional Patent Application Ser. No. 60 / 514,094, filed Oct. 24, 2003.FEDERALLY SPONSORED RESEARCH[0002]Not ApplicableSEQUENCE LISTING OR PROGRAM[0003]Not ApplicableBACKGROUND OF THE INVENTION[0004]1. Field of the Invention[0005]This invention relates generally to image processing systems and more particularly to a system and method for automatic extraction of demographic information (age, gender, or ethnicity) from an image.[0006]2. Background of the Invention[0007]Human faces provide us with a plethora of information that is valuable and necessary for social interaction. When we encounter a face, we can quickly and successfully decide whether it is one we know. For faces of people we know, we can easily retrieve semantic and identity information about the person. Furthermore, from both familiar and unfamiliar faces we can make gender, ethnicity, and age estimation for a person.[0008]Autom...

AI Technical Summary

Benefits of technology

[0038]FIG. 13 shows an exemplary embodiment of the Parallel Configuration for multiple Category Demographic Classifiers (for e.g., two or more categories of age, gender, or ethnicit...

Problems solved by technology

Furthermore, their system cannot be applied in the current form for ethnicity and gender classification.

Furthermore, Poggio's patent does not use or does not clarify the classifier fusion mechanism.

There system is not suited to demographic classification as probabilistic model for any two demographics class are very similar to each other and hence undistinguishable.

Moreover, they did not show that their system could be applied to Ethnicity and age classification.

Images